PulseAugur
EN
LIVE 07:07:49

LLM agent InternGeometry achieves Olympiad-level geometry problem-solving

By PulseAugur Editorial · [1 sources] ·

Researchers have developed InternGeometry, an LLM agent capable of solving International Mathematical Olympiad (IMO) level geometry problems. This agent overcomes limitations in proposing auxiliary constructions by iteratively suggesting, verifying with a symbolic engine, and learning from feedback. InternGeometry achieved a score of 44 out of 50 on IMO geometry problems from 2000-2024, surpassing the average gold medalist score, and utilized significantly less training data than previous expert models like AlphaGeometry 2. AI

IMPACT Demonstrates LLM agents can reach expert-level performance on specialized, complex tasks with significantly less data.

RANK_REASON The cluster describes a research paper detailing a new method for LLM agents to solve complex geometry problems. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

LLM agent InternGeometry achieves Olympiad-level geometry problem-solving

How we ranked this

Signal score
24 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster describes a research paper detailing a new method for LLM agents to solve complex geometry problems. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · Haiteng Zhao, Junhao Shen, Yiming Zhang, Songyang Gao, Kuikun Liu, Tianyou Ma, Fan Zheng, Dahua Lin, Wenwei Zhang, Kai Chen ·

    Achieving Olympiad-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning

    arXiv:2512.10534v4 Announce Type: replace Abstract: Large language model (LLM) agents exhibit strong mathematical problem-solving abilities and can even solve International Mathematical Olympiad (IMO) level problems with the assistance of formal proof systems. However, due to wea…

RELATED ENTITIES

RELATED TOPICS